nace-ai/kapitsa
Blazing fast Apple Silicon optimized inference engine built for Qwen & Nemotron. OpenAI + Anthropic API compatible. Built by folks from nace.ai
Older snapshot: check the original source for current information.
From the publisher
README & documentation
Source previewRead the project’s overview, installation instructions and usage examples. The original README is the source of truth.
Kapitsa is an inference engine for Apple silicon that runs Qwen, Nemotron and Recursive's Flint models locally, built for coding agents. It starts opencode, Claude Code, Codex or pi on a local model, and serves OpenAI and Anthropic APIs. Benchmarks · Quickstart · CLI · Models · How KFlash works · Docs Kapitsa has the fastest decode in 32 of the 37 model and Mac pairs measured against nine engines (how each number was measured). Each cell reads prefill / decode in tokens per second. Prefill is a 4K-token prompt, decode a 512-token answer at T 0.6 (Flint at its card's T 1.0). × cannot run that model · — not measured. How these were measured, run dates and flags: docs/benchmarks.md. The poster's numbers, and the models it leaves out, are in each Mac's table under Models. Every recorded run, with its Mac, model, prefill and decode speed, is in…
Read the full README ↗ · Preview checked 2026-10-27T18:27:30.155Z
Inside the original README — Document outline
Headings are captured from the source. Links open the publisher’s document, not a locally hosted copy.
Links from the README
References supplied by the publisher, not independently verified endorsements. Check the destination before downloading files or entering credentials.
Documentation belongs to its respective authors. Reported project/model license: Apache-2.0. A listing is not a grant of reuse or training rights. Confirm the document’s own terms at the source.
What this repository does
Blazing fast Apple Silicon optimized inference engine built for Qwen & Nemotron. OpenAI + Anthropic API compatible. Built by folks from nace.ai
Repository facts
- Owner
- nace-ai
- Primary language
- C++
- Stars
- 373
- Forks
- 55
- Open issues + pull requests
- 13
- License
- Apache-2.0
- Archived
- No
- Default branch
- main
- Created
- 2026-10-16T00:41:59.000Z
- Last push
- 2026-10-23T12:04:33.000Z
Topics and intended use
No topics were included in the latest source metadata.
Review the README for scope, installation, examples and limitations. We do not run repository code or certify it.
Evaluate before installing
Review licensing and dependencies, inspect recent commits and unresolved issues, and test in an isolated environment before production use. Stars and forks alone cannot answer these questions.
Source and freshness
Source: GitHub. Metadata observed 2026-10-23T12:13:06.193Z. Daily imports are snapshots, not real-time monitoring.
Popularity and source listings do not establish security, suitability, licensing rights or benchmark performance.